Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: Panel data + stochastic frontier (xtfrontier)


From   smerryman@kc.rr.com
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Panel data + stochastic frontier (xtfrontier)
Date   Wed, 29 Sep 2004 12:33:52 -0500

Sumon,

It is typical to use the likelihood ratio test to compare the Cobb-Douglas and the traslog.  
I believe Tim Coelli (around 1995) showed that the Wald test has low power compared to the 
likelihood ratio test.

Also, rom the -lrtest- helpfile: 
 
"lrtest provides an important alternative to Wald testing for models fitted by maximum
likelihood.  Wald testing requires fitting only one model (the unrestricted model).
Hence, it is computationally more attractive than likelihood-ratio testing.  Most
statisticians, however, favor using likelihood ratio testing whenever feasible since
the null-distribution of the LR test statistic is often "more closely" chi-square
distributed than the Wald test statistic."

You could do the following

*estimate translog
qui xtfrontier ....
est store A
*est Cobb Douglas
qui xtfrontier....
lrtest A

Hope this helps,
Scott


----- Original Message -----
From: Dev Vencappa <lexdvv@nottingham.ac.uk>
Date: Wednesday, September 29, 2004 10:09 am
Subject: Re: st: Panel data + stochastic frontier (xtfrontier)

> >>
> Sumon, 
> if the problem is only about testing between the two functional 
> forms, then a simple solution is to test the joint significance of 
> the extra parameters on the Translog function, using an F test for 
> instance, using a pooled regression in the first place. That 
> should help you decide between the two. Once you have done that, 
> you can then run the xtfrontier command on your preferred 
> functional form. Also, you may want to look at the constraints 
> option in the xtfrontier command.  But then, there may be other 
> better ways.
> 
> 
> Dev
> 
> 
> >>> s.bhaumik@qub.ac.uk 29/09/04 16:01:22 >>>
> Hi,
> 
> I would like to use the xtfrontier command in Stata to estimate
> a stochastic frontier model for panel data. Now, stochastic
> frontier models can have Cobb-Douglas or translog functional
> forms. Hence, there has to be a way to test which one of these
> functional form better fits the data, and then use that functional
> form for the estimation. How can one do that in the context of the
> xtfrontier command?
> 
> Regards,
> 
> Sumon
> 
> ___________________________________
> Dr. Sumon Kumar Bhaumik
> School of Management and Economics
> Queen's University Belfast
> 25 University Square
> Belfast BT7 1NN
> Phone: +44 28 9097-3273
> Web page: http://www.qub-efrg.com/staff/sbhaumik/ 
> Emerging Markets Finace & Trade
> (http://www.mesharpe.com/results1.asp?ACR=REE)
> Eurasian Review of Economics and Finance 
> (http://www.managementschool.ed.ac.uk/research/journals/eref/)
> 
> 
> *
> *   For searches and help try:
> *   http://www.stata.com/support/faqs/res/findit.html 
> *   http://www.stata.com/support/statalist/faq 
> *   http://www.ats.ucla.edu/stat/stata/
> 
> 
> This message has been scanned but we cannot guarantee that it and any
> attachments are free from viruses or other damaging content: you are
> advised to perform your own checks.  Email communications with the
> University of Nottingham may be monitored as permitted by UK 
> legislation.
> 
> *
> *   For searches and help try:
> *   http://www.stata.com/support/faqs/res/findit.html
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
> 

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index